diff_of_means ratio_of_sd monthly_amplitude_ratio_of_means sign_correlation qqplot_mae acf_mae extremogram_mae
lstm.mri_esm2_0.ssp434 -0.38% 0.735 0.603 0.494 8.431 0.095 0.037
lstm.mri_esm2_0.ssp245 -0.55% 0.728 0.572 0.503 8.788 0.095 0.044
lstm.ec_earth3.ssp434 0.87% 0.709 0.569 0.496 8.597 0.080 0.048
nv.mri_esm2_0.ssp245 1.46% 0.791 0.852 0.508 7.575 0.132 0.019
lstm.cesm2.ssp245 1.52% 0.721 0.601 0.498 8.039 0.072 0.037
lstm.cesm2.ssp370 1.97% 0.763 0.668 0.494 6.918 0.049 0.033
lstm.mri_esm2_0.ssp370 3.06% 0.704 0.576 0.502 8.095 0.124 0.044
nv.mri_esm2_0.ssp434 -3.13% 0.818 0.856 0.505 6.940 0.155 0.025
lstm.cesm2.ssp585 5.80% 0.717 0.622 0.494 7.864 0.081 0.031
xgboost.mri_esm2_0.ssp370 6.57% 0.851 0.820 0.500 5.274 0.040 0.023
nv.mri_esm2_0.ssp370 -6.97% 0.822 0.887 0.491 6.935 0.117 0.021
xgboost.cesm2.ssp245 -7.04% 0.791 0.795 0.511 5.990 0.031 0.021
xgboost.mri_esm2_0.ssp434 9.10% 0.829 0.803 0.517 6.402 0.056 0.042
xgboost.cesm2.ssp585 -9.44% 0.778 0.780 0.512 6.753 0.031 0.020
xgboost.cesm2.ssp370 -9.62% 0.774 0.773 0.504 6.883 0.033 0.022
xgboost.mri_esm2_0.ssp245 13.19% 0.830 0.812 0.508 7.938 0.042 0.028
cnn.mri_esm2_0.ssp370 -16.51% 1.178 1.116 0.498 8.124 0.056 0.046
cnn.mri_esm2_0.ssp245 -18.60% 1.186 1.132 0.504 9.203 0.083 0.048
cnn.ec_earth3.ssp434 -19.61% 1.274 1.153 0.501 9.644 0.069 0.049
cnn.mri_esm2_0.ssp434 -20.10% 1.270 1.174 0.473 9.970 0.094 0.050
cnn.cesm2.ssp245 -20.72% 1.356 1.246 0.506 10.187 0.050 0.036
cnn.cesm2.ssp370 -20.73% 1.419 1.292 0.483 10.313 0.065 0.053
nv.cesm2.ssp245 -21.42% 0.830 0.882 0.512 10.557 0.060 0.019
cnn.cesm2.ssp585 -22.59% 1.392 1.247 0.501 11.118 0.070 0.044
xgboost.ec_earth3.ssp434 -23.42% 0.759 0.758 0.499 11.728 0.078 0.036
nv.cesm2.ssp370 -24.55% 0.841 0.885 0.511 12.067 0.063 0.026
nv.cesm2.ssp585 -25.09% 0.828 0.909 0.520 12.331 0.054 0.022
nv.ec_earth3.ssp434 -32.87% 0.783 0.846 0.493 16.156 0.070 0.024

Time series of the first days

Distribution of daily values by month

QQ Plot

Distribution of the undownscaled value on days with estimated extremes values.

On the x-axis we have the daily mean (standardized). It says Undownscaled value, but is the daily mean after the downscaling. A good idea is to plot the original undownscaled value.

The purpose of this plot is to illustrate the distribution of P(undownscaled value | we predicted an extreme). This is useful because it reveals how much information we can recover concerning extreme events. If the distribution is skewed to the right, it suggests that we’re predicting extreme values only when extreme values have already occurred. Conversely, if the lower tail of the distribution resembles the reanalysis data, it indicates that we can capture short-duration extremes (e.g., brief periods of heavy rainfall, such as an intense downpour lasting an hour before stopping).

Autocorrelogram

Extremogram